Loading...
156 results
Search Results
Now showing 1 - 10 of 156
- Motion sensors for Knee angle recognition in muscle rehabilitation solutionsPublication . Franco, Tiago; Oliveira, Leonardo Sestrem de; Henriques, Pedro Rangel; Alves, Paulo; Pereira, Maria João; Brandão, Diego; Leitão, Paulo; Silva, AlfredoThe progressive loss of functional capacity due to aging is a serious problem that can compromise human locomotion capacity, requiring the help of an assistant and reducing independence. The NanoStim project aims to develop a system capable of performing treatment with electrostimulation at the patient’s home, reducing the number of consultations. The knee angle is one of the essential attributes in this context, helping understand the patient’s movement during the treatment session. This article presents a wearable system that recognizes the knee angle through IMU sensors. The hardware chosen for the wearables are low cost, including an ESP32 microcontroller and an MPU-6050 sensor. However, this hardware impairs signal accuracy in the multitasking environment expected in rehabilitation treatment. Three optimization filters with algorithmic complexity O(1) were tested to improve the signal’s noise. The complementary filter obtained the best result, presenting an average error of 0.6 degrees and an improvement of 77% in MSE. Furthermore, an interface in the mobile app was developed to respond immediately to the recognized movement. The systems were tested with volunteers in a real environment and could successfully measure the movement performed. In the future, it is planned to use the recognized angle with the electromyography sensor.
- A Neural Network-Based Approach to Identifying Wrinkles and Recommending Cosmetic ProductsPublication . Tonello, Guilherme de M.; Alves, Paulo; Ortoncelli, André Roberto; Pereira, Maria JoãoSkincare has become a constant demand among the population, who are increasingly concerned about their health. Furthermore, environmental issues arouse the interest of the masses in natural and sustainable products. This project proposes an approach for recommending thermal-based products based on a set of information provided by the user, combined with the results of computer vision algorithms (to identify the age and occurrence of wrinkles on the user’s forehead). A list of recommended products is generated Based on the profile determined for the user. To predict wrinkles, for each facial image sent by the user, we apply a pre-processing step that segments and prepares the region of interest, which a CNN will process. As a CNN, we used the VGG16 architecture trained using a transfer learning and fine-tuning strategy, which improved the results obtained, reaching an accuracy of 92% in classifying wrinkles. An algorithm provided by the Deepface tool is used to predict the user’s age, based on the sent picture.Which is crossed with the user’s information to determine a level of aging in order to improve the quality of the recommended products.
- Using academic analytics to predict dropout risk in engineering coursesPublication . Lima, Jhonny de; Alves, Paulo; Pereira, Maria João; Almeida, SimoneThe increase of data generated and stored in the educational databases makes it possible to obtain essential information about the teaching and learning process. School dropout and performance problems continue to represent issues which challenge teachers, researchers and higher education institutions to seek solutions. Through the use of academic analytics techniques for data analysis, a sample of 1,844 students between graduates and dropouts on the period between 2007 and 2015 were used as the basis. The methodology followed is essentially quantitative and it allowed to compare student profiles and degrees based on scores, number of attempts and other performance indicators. The data set was processed using Excel software for statistical analysis and R software for data mining using the k-Means and C5.0 algorithms. The propose of a model based on decision trees has as main objectives the generation of standardized instructions, easy interpretation and allow the addition of several possible outcomes, contributing to the decision-making process. The results of this study resulted in contributions which enable higher education institutions to identify students with performance problems and those at risk of dropout and, therefore, allow teachers and course directors to adopt better strategies to increase success and reduce dropout.
- Measuring the understandability of WSDL specifications, web service understanding degree approach and systemPublication . Berón, Mario; Bernardis, Hernán; Miranda, Enrique; Riesco, Daniel; Pereira, Maria João; Henriques, Pedro RangelWeb Services (WS) are fundamental software artifacts for building service oriented applications and they are usually reused by others. Therefore they must be analyzed and comprehended for maintenance tasks: identification of critical parts, bug fixing, adaptation and improvement. In this article, WSDLUD a method aimed at measuring a priori the understanding degree (UD) of WSDL (Web Service Description Language) descriptions is presented. In order to compute UD several criteria useful to measure the understanding’s complexity of WSDL descriptions must be defined. These criteria are used by LSP (Logic Scoring of Preference), a multicriteria evaluation method, for producing a Global Preference value that indicates the satisfaction level of the WSDL description regarding the evaluation focus, in this case, the understanding degree. All the criteria information required by LSP is extracted from WSDL descriptions by using static analysis techniques and processed by specific algorithms which allow gathering semantic information. This process allows to obtain a priori information about the comprehension difficulty which proves our research hypotheses that states that it is possible to compute the understanding degree of a WSDL description.
- Concepção e especificação de uma linguagem visualPublication . Pereira, Maria JoãoO desenvolvimento de um compilador para a linguagem TSC (Timed StateCharts)- linguagem textual que descreve máquinas de estados temporizadas com transições condicionais - constitui o objectivo inicial deste estudo. Em primeiro lugar, foram revistos alguns conceitos básicos relacionados com compiladores, gramáticas de atributos e geração de compiladores. Foi necessário compreender a utilização das máquinas de estados na descrição do comportamento de sistemas reactivos, os diagramas TSC e a sua representação na linguagem TSC. No seguimento do estudo foram definidos os requisitos do compilador já referido, o qual tem como tarefa implementar um conjunto de regras de tradução de diagramas TSC em axiomas lógicos RTL - (Real Time Logic). No desenvolvimento desse compilador foi utilizado o sistema ELI. No entanto o objectivo principal deste estudo consiste em criar meios para que seja possível a tradução directa dos diagramas TSC nos axiomas RTL. Para tal, foi criada uma linguagem visual para a escrita de TSC's. Posteriormente esta nova linguagem foi especificada usando o formalismo MASOVILA.
- VisualLISA: a visual environment to develop attribute grammarsPublication . Oliveira, Nuno; Pereira, Maria João; Henriques, Pedro Rangel; Cruz, Daniela; Cramer, BastianThe focus of this paper is on crafting a new visual language for attribute grammars (AGs), and on the development of the associated programming environment. We present a solution for rapid development of VisualLISA editor using DEViL. DEViL uses traditional attribute grammars, to specify the language’s syntax and semantics, extended by visual representations to be associated with grammar symbols. From these specifications a visual programming environment is automatically generated. In our case, the environment allows us to edit a visual description of an AG that is automatically translated into textual notations, including an XML-based representation for attribute grammars (XAGra), and is intended to be helpful for beginners and rapid development of small AGs. XAGra allows us to use VisualLISA with other compiler-compiler tools.
- Data mining tool for academic data exploitation: publication report on engineering students profilesPublication . Barbu, Marian; Vilanova, Ramon; Vicario, José; Pereira, Maria João; Alves, Paulo; Podpora, Michal; Kawala-Janik, A.; Prada, Miguel Angel; Dominguez, Manuel; Spagnolini, Anna; Fontana, L.This report summarizes the findings of the project SPEET. It relies on the initial document generated as Intellectual Output #1 and the results obtained by application of the IT tools developed in Intellectual Output #2, and Intellectual Output #3 to the academic data provided by the partner institutions. The main objectives of applying analytic techniques to evaluate the academic data sources can be categorized as follows: Improve Student Results; Create Mass-customized Programs; Improve the Learning Experience in Real-time; Reduce Dropouts and Increase Results.
- Simulador gráfico de algoritmos matemáticosPublication . Alves, Luís M.; Balsa, Carlos; Pereira, Maria JoãoO objetivo principal do trabalho de investigação foi desenvolver uma ferramenta computacional que possa ser usada por professores e alunos no ensino dos Métodos Numéricos. A ferramenta, designada por GraSMA (Graphical Simulator of Mathematical Algorithms), permite visualizar no ecrã a execução dos correspondentes algoritmos. Esta ferramenta integra vários softwares open source e baseia-se na anotação automática de código Octave com funções de inspeção que permitem captar a sucessão de valores e produzir uma animação do funcionamento do método. A validação do GraSMA como ferramenta de apoio à lecionação destes métodos foi feita através de uma experiência feita em contexto de sala de aula que obteve resultados muito positivos conforme será descrito neste artigo em contexto de sala de aula que obteve resultados muito positivos conforme neste artigo.
- Graphical simulator of mathematical algorithmsPublication . Quintin, Kévin; Pereira, Maria João; Balsa, CarlosThe main objective of our work is to develop a tool (Graphical Simulator of Mathematical Algorithms - GraSMA) that can be used by teachers and students in the classes of Numerical Methods. GraSMA will screen the execution of mathematical algorithms coded in Octave. For the end user, the software is therefore a sequence of parameterized algorithms whose steps can be visualized graphically. To achieve it we try two different strategies. We started by annotating manually the original algorithm with inspector functions. Now we are testing a new approach that aims at automatically annotating the original code with inspector functions. A language processor, built with Lex and Yacc tools, will be used to automatically annotate Octave code with inspection function. Until now, this task has been applied to a particular class of numerical algorithms that calculates zeros of nonlinear functions. The objective now is to extend this strategy to a larger class of numerical methods. This application permits to simulate mathematical methods. So, users can have a better understanding of mathematical methods. However, we think this application can’t be completely generic and if we want to display complex algorithm, it will be hard and slow. Indeed, we think that Java isn’t the best language to deal with mathematics, C could be better.
- Code inspection approaches for program visualizationPublication . Cruz, Daniela; Berón, Mario; Henriques, Pedro Rangel; Pereira, Maria JoãoThe aim of this paper is to show the approaches involved in the implementation of two tools of PCVIA project that can be used for Program Comprehension. Both tools use known compiler techniques to inspect code in order to visualize and understand programs’ execution but one of them modifies the source code and the other not. In the non-invasive approach, we convert the source program into an internal decorated (or attributed) abstract syntax tree and then we visualize the structure traversing it, and applying visualization rules at each node according to a pre-defined rule-base. No changes are made in the source code, and the execution is simulated. In the invasive approach, we traverse the source program and instrument it with inspection functions. Those functions, also known as inspectors, provide information about the function-call flow and data usage at runtime (during the actual program execution). This information is collected and gathered in an information repository that is then displayed in a suitable form for navigation. These two different approaches are used respectively by Alma (generic program animation system) and CEAR (C Rooting Algorithm Visualization tool). For each tool several examples of visualization are shown in order to discuss the information that is included in the visualizations, visualization types and the use of Program Animation for Program Comprehension.